© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77583
    Prev
    Next
    INDEX
    Explanations

    national anthems and marches

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    書館
    -0.79
    之助
    -0.75
    judice
    -0.75
     novedad
    -0.75
    чним
    -0.74
     Wissenschaften
    -0.74
    璘
    -0.74
    ⃣
    -0.73
    ALLOW
    -0.73
    瓏
    -0.73
    POSITIVE LOGITS
    Deutschland
    0.82
     cocktails
    0.79
     Marse
    0.77
    ="/"
    0.75
     Internationale
    0.75
     alten
    0.73
     bug
    0.72
     Hail
    0.71
     Tien
    0.71
    Ң
    0.71
    Activations Density 0.022%

    No Known Activations